THE ACADEMY / LOCAL AI 101
Learn the stack
one layer at a time.
Short, practical lessons for installing, sizing, prompting, evaluating and maintaining offline models.
06guided tracksFrom first pull to production habits
01 / START
Local AI fundamentals
Runtimes, model files, quantization, context, RAM and VRAM.
02 / INSTALLInstall on Windows
Ollama setup, verification and the first local run.
03 / INSTALLInstall on Linux
GPU drivers, services and runtime checks.
04 / INSTALLInstall on macOS
Apple Silicon, unified memory and MLX.
05 / MEASUREQuantization and benchmarks
Understand Q4, Q5, Q6, Q8 and FP16 trade-offs.
06 / OPERATETroubleshooting
Diagnose memory, speed, context, port and tool issues.